IEEE ICASSP 2022

2022 IEEE International Conference on Acoustics, Speech and Signal Processing

7-13 May 2022
  • Virtual (all paper presentations)
22-27 May 2022
  • Main Venue: Marina Bay Sands Expo & Convention Center, Singapore
27-28 October 2022
  • Satellite Venue: Crowne Plaza Shenzhen Longgang City Centre, Shenzhen, China

ICASSP 2022
MLSP-40.3

PRUNING BY TRAINING: A NOVEL DEEP NEURAL NETWORK COMPRESSION FRAMEWORK FOR IMAGE PROCESSING

Guanzhong Tian, Zhejiang University, China

Session:
Deep Learning VI

Track:
Machine Learning for Signal Processing

Location:
Gather Area F

Presentation Time:
Thu, 12 May, 20:00 - 20:45 China Time (UTC +8)
Thu, 12 May, 12:00 - 12:45 UTC

Session Chair:
Massimiliano Todisco, EURECOM
Presentation
Discussion
Resources
No resources available.
Session MLSP-40
MLSP-40.1: Win the Lottery Ticket via Fourier Analysis: Frequencies Guided Network Pruning
Yuzhang Shang, Bin Duan, Yan Yan, Illinois Institute of Technology, United States of America; Ziliang Zong, Texas State University, United States of America; Liqiang Nie, Shandong University, China
MLSP-40.2: SPARSEBFA: ATTACKING SPARSE DEEP NEURAL NETWORKS WITH THE WORST-CASE BIT FLIPS ON COORDINATES
Kyungmi Lee, Anantha P. Chandrakasan, Massachusetts Institute of Technology, United States of America
MLSP-40.3: PRUNING BY TRAINING: A NOVEL DEEP NEURAL NETWORK COMPRESSION FRAMEWORK FOR IMAGE PROCESSING
Guanzhong Tian, Zhejiang University, China
MLSP-40.4: ADVERSARIAL EXAMPLES DETECTION BASED ON ERROR LEVEL ANALYSIS AND SPACE MAPPING
Sizhao Huang, Shuai Wang, Jian Chen, Guozhi Li, School of Information and Communication Engineering University of Electronic Science and Technology of China;Yangtze Delta Region Institute of University of Electronic Science and Technology of China, China; Wenyi Wang, School of Information and Communication Engineering University of Electronic Science and Technology of China, China
MLSP-40.5: LEARNING MONOCULAR 3D HUMAN POSE ESTIMATION WITH SKELETAL INTERPOLATION
Ziyi Chen, Shang-Hong Lai, National Tsing Hua University, Taiwan; Akihiro Sugimoto, National Institute of Informatics, Japan
MLSP-40.6: TRAINING STABLE GRAPH NEURAL NETWORKS THROUGH CONSTRAINED LEARNING
Juan Cervino, Luana Ruiz, Alejandro Ribeiro, University of Pennsylvania, United States of America